codebase-cleanup-deps-audit

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's implementation playbook explicitly fetches and parses data from public third-party sources (e.g., npm registry API, PyPI package JSON endpoints, bundlephobia API shown in resources/implementation-playbook.md), and that untrusted package/advisory metadata is read and used to drive vulnerability prioritization, automated remediation, and PR generation, which could allow indirect prompt-injection via crafted upstream content.